© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53144
    Prev
    Next
    INDEX
    Explanations

    poetry and writing programs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åī§ä¸Ń
    -0.11
    鸱
    -0.10
     ìĿĺìĤ¬
    -0.10
    èĭ±éĽĦ
    -0.09
    åł¡
    -0.09
    Scient
    -0.09
    skip
    -0.09
     filmed
    -0.09
    å½ķåĥı
    -0.09
    ifu
    -0.09
    POSITIVE LOGITS
    ä½ľåĵģ
    0.13
    è¯ĹæŃĮ
    0.13
    çļĦä½ľåĵģ
    0.12
     poetry
    0.11
    ä½ľå®¶
    0.11
    åĪĽä½ľ
    0.10
    ìŀij
    0.10
    æĸĩåѦ
    0.10
     Poetry
    0.10
    ä½ľåĵģåĨħ容
    0.10
    Activations Density 0.179%

    No Known Activations